scRNASeq

#Convert("all_samples.h5ad", dest = "h5seurat", overwrite = T)
seurat_anndata = LoadH5Seurat("all_samples.h5seurat",  assays = "RNA")

## Validating h5Seurat file

## Initializing RNA with data

## Adding counts for RNA

## Adding scale.data for RNA

## Adding feature-level metadata for RNA

## Adding reduction harmony

## Adding cell embeddings for harmony

## Adding miscellaneous information for harmony

## Adding reduction pca

## Adding cell embeddings for pca

## Adding feature loadings for pca

## Adding miscellaneous information for pca

## Adding reduction umap

## Adding cell embeddings for umap

## Adding miscellaneous information for umap

## Adding command information

## Adding cell-level metadata

levels(seurat_anndata@meta.data$sample)

##  [1] "8356"  "11522" "11817" "11918" "12889" "12929" "12935" "13634" "13636"
## [10] "13774" "14428" "14958" "14965" "15002" "15467"

clinical.data <- data.frame(read.csv("/home/marcelo/LungPredict1/RawFiles/ColumnData_Vanderbilt.csv", row.names = 1))
clinical.data <- clinical.data[,c(1,5,6,9,11,13)]

coldata = clinical.data[clinical.data$pt_ID%in%levels(seurat_anndata@meta.data$sample),]
#14958 14965 11817 13634 15467 12929  8356 12889 15002
#"R3388_YZ_1"  "R3388_YZ_2"  "R3388_YZ_10" "R3388_YZ_11" "R3388_YZ_18" "R3388_YZ_28" "R3388_YZ_56" "R4163_YZ_16" "R4163_YZ_25"

Clustering

DimPlot(seurat_anndata, reduction="umap")

ElbowPlot(seurat_anndata) #determine dimensionality of data

seurat_anndata = FindNeighbors(seurat_anndata, dims = 1:20)

## Computing nearest neighbor graph

## Computing SNN

seurat_anndata = FindClusters(seurat_anndata, resolution = 1)

## Modularity Optimizer version 1.3.0 by Ludo Waltman and Nees Jan van Eck
## 
## Number of nodes: 44876
## Number of edges: 1487565
## 
## Running Louvain algorithm...
## Maximum modularity in 10 random starts: 0.8737
## Number of communities: 25
## Elapsed time: 10 seconds

DimPlot(seurat_anndata, reduction="umap", label = T)

Manual annotation

Find markers (one cluster vs all others)

markers = FindAllMarkers(seurat_anndata,
               logfc.threshold = 0.25, #min logfc 
               min.pct = 0.1, #genes that are detected on 50% frequency across clusters
               only.pos = T,
               test.use = 'wilcox',
               slot = 'counts')

## Calculating cluster 0

## Calculating cluster 1

## Calculating cluster 2

## Calculating cluster 3

## Calculating cluster 4

## Calculating cluster 5

## Calculating cluster 6

## Calculating cluster 7

## Calculating cluster 8

## Calculating cluster 9

## Calculating cluster 10

## Calculating cluster 11

## Calculating cluster 12

## Calculating cluster 13

## Calculating cluster 14

## Calculating cluster 15

## Calculating cluster 16

## Calculating cluster 17

## Calculating cluster 18

## Calculating cluster 19

## Calculating cluster 20

## Calculating cluster 21

## Calculating cluster 22

## Calculating cluster 23

## Calculating cluster 24

head(markers)

##          p_val avg_log2FC pct.1 pct.2 p_val_adj cluster     gene
## MS4A1        0   1.559624 0.904 0.038         0       0    MS4A1
## HLA-DRA      0   1.519554 0.987 0.267         0       0  HLA-DRA
## HLA-DQA1     0   1.241250 0.946 0.277         0       0 HLA-DQA1
## CD79A        0   1.217081 0.841 0.136         0       0    CD79A
## CD83         0   1.139373 0.771 0.156         0       0     CD83
## HLA-DQB1     0   1.119662 0.920 0.309         0       0 HLA-DQB1

features = c('NKG7', 'IL7R', 'HLA-DRA','IGHG1','BATF','IGFBP7', 'TYROBP', 'RAMP2','TYMS','TPSAB1','WFDC2','SFRP21')
RidgePlot(seurat_anndata, features = features, ncol = 3)

## Warning in FetchData.Seurat(object = object, vars = features, slot = slot): The
## following requested variables were not found: SFRP21

## Picking joint bandwidth of 0.0686

## Picking joint bandwidth of 0.114

## Picking joint bandwidth of 0.0942

## Picking joint bandwidth of 0.0628

## Picking joint bandwidth of 0.064

## Picking joint bandwidth of 0.055

## Picking joint bandwidth of 0.0322

## Picking joint bandwidth of 0.00837

## Picking joint bandwidth of 0.00972

## Picking joint bandwidth of 0.011

## Picking joint bandwidth of 0.0369

VlnPlot(seurat_anndata, features = features)

## Warning in FetchData.Seurat(object = object, vars = features, slot = slot): The
## following requested variables were not found: SFRP21

FeaturePlot(seurat_anndata, features = features)

## Warning in FetchData.Seurat(object = object, vars = c(dims, "ident", features),
## : The following requested variables were not found: SFRP21

Automatic cell annotation (ATLAS)

ref = celldex::HumanPrimaryCellAtlasData()

## snapshotDate(): 2022-04-26

## see ?celldex and browseVignettes('celldex') for documentation

## loading from cache

## see ?celldex and browseVignettes('celldex') for documentation

## loading from cache

single_counts = GetAssayData(seurat_anndata, slot='counts')
pred = SingleR(test = single_counts, 
        ref = ref,
        labels = ref$label.main)

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

head(pred)

## DataFrame with 6 rows and 5 columns
##                                            scores first.labels
##                                          <matrix>  <character>
## AAACCTGAGCTTTGGT-1 0.128861:0.245469:0.212046:...      NK_cell
## AAACCTGCACCAGGCT-1 0.139778:0.303035:0.281091:...      T_cells
## AAACGGGGTACTCTCC-1 0.147528:0.257401:0.271606:...           DC
## AAACGGGTCGACCAGC-1 0.111915:0.261614:0.254842:...      T_cells
## AAAGCAAAGACAAGCC-1 0.159956:0.297482:0.273721:...      NK_cell
## AAAGCAACAAGCCCAC-1 0.132399:0.278978:0.237570:...      T_cells
##                        tuning.scores      labels pruned.labels
##                          <DataFrame> <character>   <character>
## AAACCTGAGCTTTGGT-1 0.286362:0.188706     NK_cell       NK_cell
## AAACCTGCACCAGGCT-1 0.368637:0.247717     T_cells       T_cells
## AAACGGGGTACTCTCC-1 0.339815:0.295807          DC            DC
## AAACGGGTCGACCAGC-1 0.285696:0.201506     T_cells       T_cells
## AAAGCAAAGACAAGCC-1 0.231436:0.109418     T_cells       T_cells
## AAAGCAACAAGCCCAC-1 0.327587:0.210946     T_cells       T_cells

seurat_anndata$singleR.labels = pred$labels[match(rownames(seurat_anndata@meta.data), rownames(pred))]
DimPlot(seurat_anndata, reduction = 'umap', group.by = 'singleR.labels')

head(pred$scores)

##      Astrocyte    B_cell        BM BM & Prog. Chondrocytes       CMP        DC
## [1,] 0.1288609 0.2454694 0.2120456  0.1785377    0.1596201 0.2348847 0.2354978
## [2,] 0.1397776 0.3030350 0.2810913  0.2213133    0.1728824 0.2685374 0.2804226
## [3,] 0.1475280 0.2574010 0.2716059  0.1651107    0.1920963 0.2424944 0.4121792
## [4,] 0.1119149 0.2616144 0.2548422  0.1872333    0.1379515 0.2385703 0.2368478
## [5,] 0.1599564 0.2974818 0.2737211  0.1974025    0.1841983 0.2644691 0.2769523
## [6,] 0.1323993 0.2789778 0.2375703  0.1940324    0.1651088 0.2457796 0.2610297
##      Embryonic_stem_cells Endothelial_cells Epithelial_cells Erythroblast
## [1,]           0.11055616         0.1720191        0.1649112    0.1711534
## [2,]           0.14682796         0.2061413        0.1984771    0.2102717
## [3,]           0.11516413         0.2243761        0.2078711    0.1646774
## [4,]           0.09878323         0.1655049        0.1424403    0.1646180
## [5,]           0.15609302         0.1984647        0.1890662    0.1865274
## [6,]           0.12805750         0.1919904        0.1725622    0.1855369
##      Fibroblasts Gametocytes       GMP Hepatocytes HSC_-G-CSF HSC_CD34+
## [1,]   0.1482040   0.1447390 0.2480521   0.1421683  0.2486675 0.2373476
## [2,]   0.1682255   0.1479854 0.2823766   0.1834610  0.3267963 0.2644097
## [3,]   0.2031987   0.1604163 0.2833434   0.2027688  0.3257528 0.2971054
## [4,]   0.1292689   0.1043757 0.2480834   0.1207127  0.2895977 0.2267591
## [5,]   0.1721161   0.1500515 0.2796854   0.1733605  0.3159671 0.2598502
## [6,]   0.1643852   0.1329930 0.2548679   0.1562751  0.2895931 0.2345147
##      iPS_cells Keratinocytes Macrophage       MEP  Monocyte       MSC Myelocyte
## [1,] 0.1394411     0.1544705  0.2300599 0.2011366 0.2573516 0.1407319 0.2235121
## [2,] 0.1524905     0.1699264  0.2840576 0.2351096 0.3025898 0.1558683 0.2639280
## [3,] 0.1636068     0.1870450  0.4078145 0.1920928 0.3987618 0.1676612 0.2898561
## [4,] 0.1208349     0.1025808  0.2383048 0.2018317 0.2600235 0.1223021 0.2282195
## [5,] 0.1606894     0.1669182  0.2726076 0.2209953 0.2963006 0.1623042 0.2597675
## [6,] 0.1474047     0.1368754  0.2519917 0.2120243 0.2768807 0.1484591 0.2398599
##      Neuroepithelial_cell   Neurons Neutrophils   NK_cell Osteoblasts Platelets
## [1,]           0.09700509 0.1359534   0.2537397 0.3069176   0.1431023 0.1829822
## [2,]           0.11660883 0.1569972   0.2927893 0.3508412   0.1509951 0.2332163
## [3,]           0.09467130 0.1909475   0.3675563 0.2717566   0.1831689 0.2175084
## [4,]           0.07989130 0.1365315   0.2374779 0.3070698   0.1262604 0.2248319
## [5,]           0.12961705 0.1834586   0.2782209 0.3644448   0.1620286 0.2414834
## [6,]           0.10334531 0.1631646   0.2559404 0.3233688   0.1526883 0.2199729
##      Pre-B_cell_CD34- Pro-B_cell_CD34+ Pro-Myelocyte Smooth_muscle_cells
## [1,]        0.2703212        0.2400679     0.2212136           0.1496663
## [2,]        0.3417694        0.2794768     0.2570039           0.1643441
## [3,]        0.3381400        0.2465303     0.2703544           0.1918451
## [4,]        0.2981949        0.2452074     0.2285450           0.1330463
## [5,]        0.3316083        0.2753085     0.2575988           0.1716137
## [6,]        0.3012617        0.2530245     0.2269616           0.1630644
##        T_cells Tissue_stem_cells
## [1,] 0.2784824         0.1696429
## [2,] 0.3633034         0.1775285
## [3,] 0.2523547         0.2081034
## [4,] 0.3129331         0.1419393
## [5,] 0.3636598         0.1965812
## [6,] 0.3329824         0.1699385

plotScoreHeatmap(pred)

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

plotDeltaDistribution(pred)

## Warning: useNames = NA is deprecated. Instead, specify either useNames = TRUE
## or useNames = TRUE.

## Warning: Groups with fewer than two data points have been dropped.

## Warning in max(data$density): no non-missing arguments to max; returning -Inf

## Warning: Computation failed in `stat_ydensity()`
## Caused by error in `$<-.data.frame`:
## ! replacement has 1 row, data has 0

## Warning: Groups with fewer than two data points have been dropped.

## Warning in max(data$density): no non-missing arguments to max; returning -Inf

## Warning: Computation failed in `stat_ydensity()`
## Caused by error in `$<-.data.frame`:
## ! replacement has 1 row, data has 0

tab = table(Assigned = pred$labels, Clusters = seurat_anndata$seurat_clusters)
pheatmap(log10(tab+10), color=colorRampPalette(c('white', 'blue'))(10))

Extract NK cluster (cluster = 8) for further analysis

Idents(seurat_anndata) <- "seurat_clusters" 
NK = subset(seurat_anndata, idents = "8", invert = FALSE)
DimPlot(NK, reduction="umap")

NK clustering

ElbowPlot(NK) #determine dimensionality of data

NK<- FindNeighbors(NK, dims = 1:10)

## Computing nearest neighbor graph

## Computing SNN

NK<- FindClusters(NK, algorithm= 1, resolution = 0.15, verbose = T, graph.name = "RNA_snn")

## Modularity Optimizer version 1.3.0 by Ludo Waltman and Nees Jan van Eck
## 
## Number of nodes: 2000
## Number of edges: 71175
## 
## Running Louvain algorithm...
## Maximum modularity in 10 random starts: 0.8760
## Number of communities: 2
## Elapsed time: 0 seconds

NK<- RunUMAP(NK, dims = 1:10)

## Warning: The default method for RunUMAP has changed from calling Python UMAP via reticulate to the R-native UWOT using the cosine metric
## To use Python UMAP via reticulate, set umap.method to 'umap-learn' and metric to 'correlation'
## This message will be shown once per session

## 18:37:50 UMAP embedding parameters a = 0.9922 b = 1.112

## 18:37:50 Read 2000 rows and found 10 numeric columns

## 18:37:50 Using Annoy for neighbor search, n_neighbors = 30

## 18:37:50 Building Annoy index with metric = cosine, n_trees = 50

## 0%   10   20   30   40   50   60   70   80   90   100%

## [----|----|----|----|----|----|----|----|----|----|

## **************************************************|
## 18:37:51 Writing NN index file to temp file /tmp/Rtmp0ydrFV/file203b83f64acf9
## 18:37:51 Searching Annoy index using 1 thread, search_k = 3000
## 18:37:51 Annoy recall = 100%
## 18:37:52 Commencing smooth kNN distance calibration using 1 thread with target n_neighbors = 30
## 18:37:52 Initializing from normalized Laplacian + noise (using irlba)
## 18:37:52 Commencing optimization for 500 epochs, with 86322 positive edges
## 18:37:54 Optimization finished

DimPlot(NK, reduction="umap", label = T)

Differential expressed markers across clusters

markers = FindMarkers(NK, ident.1 = "0", ident.2 = "1")
head(markers)

##               p_val avg_log2FC pct.1 pct.2    p_val_adj
## GZMB   2.989360e-61  0.5385857 0.848 0.528 7.146064e-57
## FCGR3A 1.910441e-42  0.5595423 0.501 0.206 4.566909e-38
## PRF1   6.566120e-34  0.3865737 0.795 0.549 1.569631e-29
## IL7R   2.019473e-32 -0.5227357 0.222 0.456 4.827550e-28
## GNLY   1.811075e-28  0.3279821 0.882 0.685 4.329376e-24
## CTSW   2.055846e-28  0.2773990 0.914 0.732 4.914500e-24

features = c('GZMB', 'FCGR3A', 'PRF1','IL7R','GNLY','CTSW')
#features = c('CCL3', 'TIGIT', 'CD69','IRF8','IL2RB','CD160') markers from Pierre-Paul
FeaturePlot(NK, features = features)

VlnPlot(NK, features = features)

RidgePlot(NK, features = features, ncol = 2)

## Picking joint bandwidth of 0.264

## Picking joint bandwidth of 0.127

## Picking joint bandwidth of 0.241

## Picking joint bandwidth of 0.156

## Picking joint bandwidth of 0.345

## Picking joint bandwidth of 0.216

saveRDS(NK, "nk.rds")

scRNASeq_Mafe

Marcelo Hurtado

2023-04-12